# Stochastic Configuration Machines: FPGA Implementation

arXiv: https://arxiv.org/abs/2310.19225 · HTML: https://mlsanity.com/paper/2310.19225/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 50 references that are in the map.
- First posted on arXiv 30 Oct 2023.

## Builds on (most cited first, 10 of 10)

- [XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks](https://mlsanity.com/paper/1603.05279/) (2016)
- [BinaryConnect: Training Deep Neural Networks with binary weights during propagations](https://mlsanity.com/paper/1511.00363/) (2015)
- [Deep Learning with Limited Numerical Precision](https://mlsanity.com/paper/1502.02551/) (2015)
- [Stochastic Configuration Networks: Fundamentals and Algorithms](https://mlsanity.com/paper/1702.03180/) (2017)
- [Density Encoding Enables Resource-Efficient Randomly Connected Neural Networks](https://mlsanity.com/paper/1909.09153/) (2019)
- [Stochastic Configuration Machines for Industrial Artificial Intelligence](https://mlsanity.com/paper/2308.13570/) (2023)
- [Low Complexity Multiply-Accumulate Units for Convolutional Neural Networks with Weight-Sharing](https://mlsanity.com/paper/1801.10219/) (2018)
- [Stochastic Configuration Networks Ensemble for Large-Scale Data Analytics](https://mlsanity.com/paper/1707.00300/) (2017)
- [Deep Stochastic Configuration Networks with Universal Approximation Property](https://mlsanity.com/paper/1702.05639/) (2017)
- [Towards Efficient Convolutional Neural Network for Domain-Specific Applications on FPGA](https://mlsanity.com/paper/1809.03318/) (2018)

## Built on by (most cited first, 1 of 1)

- [Kernel Stochastic Configuration Networks for Nonlinear Regression](https://mlsanity.com/paper/2412.05846/) (2024)

## Abstract (arXiv)

Neural networks for industrial applications generally have additional constraints such as response speed, memory size and power usage. Randomized learners can address some of these issues. However, hardware solutions can provide better resource reduction whilst maintaining the model's performance. Stochastic configuration networks (SCNs) are a prime choice in industrial applications due to their merits and feasibility for data modelling. Stochastic Configuration Machines (SCMs) extend this to focus on reducing the memory constraints by limiting the randomized weights to a binary value with a scalar for each node and using a mechanism model to improve the learning performance and result interpretability. This paper aims to implement SCM models on a field programmable gate array (FPGA) and introduce binary-coded inputs to the algorithm. Results are reported for two benchmark and two industrial datasets, including SCM with single-layer and deep architectures.